b756ec6e80
unet's sample_size attribute is to accept tuple(h, w) in StableDiffusionPipeline ( #10181 )
2024-12-19 22:24:18 +00:00
d8825e7697
Fix failing lora tests after HunyuanVideo lora ( #10307 )
...
fix
2024-12-20 02:35:41 +05:30
074798b299
Fix local_files_only for checkpoints with shards ( #10294 )
2024-12-19 07:04:57 -10:00
3ee966950b
Allow Mochi Transformer to be split across multiple GPUs ( #10300 )
...
update
2024-12-19 22:34:44 +05:30
9764f229d4
[Single File] Add single file support for Mochi Transformer ( #10268 )
...
update
2024-12-19 22:20:40 +05:30
1826a1e7d3
[LoRA] Support HunyuanVideo ( #10254 )
...
* 1217
* 1217
* 1217
* update
* reverse
* add test
* update test
* make style
* update
* make style
---------
Co-authored-by: Aryan <aryan@huggingface.co >
2024-12-19 16:22:20 +05:30
0ed09a17bb
Check correct model type is passed to from_pretrained ( #10189 )
...
* Check correct model type is passed to `from_pretrained`
* Flax, skip scheduler
* test_wrong_model
* Fix for scheduler
* Update tests/pipelines/test_pipelines.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
* EnumMeta
* Flax
* scheduler in expected types
* make
* type object 'CLIPTokenizer' has no attribute '_PipelineFastTests__name'
* support union
* fix typing in kandinsky
* make
* add LCMScheduler
* 'LCMScheduler' object has no attribute 'sigmas'
* tests for wrong scheduler
* make
* update
* warning
* tests
* Update src/diffusers/pipelines/pipeline_utils.py
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com >
* import FlaxSchedulerMixin
* skip scheduler
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com >
2024-12-19 09:24:52 +00:00
2f7a417d1f
Update lora_conversion_utils.py ( #9980 )
...
x-flux single-blocks lora load
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
Co-authored-by: YiYi Xu <yixu310@gmail.com >
2024-12-18 23:07:50 -10:00
4450d26b63
Add Flux Control to AutoPipeline ( #10292 )
2024-12-18 22:28:56 -10:00
f781b8c30c
Hunyuan VAE tiling fixes and transformer docs ( #10295 )
...
* update
* udpate
* fix test
2024-12-19 10:28:10 +05:30
9c0e20de61
[chore] Update README_sana.md to update the default model ( #10285 )
...
Update README_sana.md to update the default model
2024-12-19 10:24:57 +05:30
f35a38725b
[tests] remove nullop import checks from lora tests ( #10273 )
...
remove nullop imports
2024-12-19 01:19:08 +05:30
f66bd3261c
Rename Mochi integration test correctly ( #10220 )
...
rename integration test
2024-12-18 22:41:23 +05:30
c4c99c3907
[tests] Fix broken cuda, nightly and lora tests on main for CogVideoX ( #10270 )
...
fix joint pos embedding device
2024-12-18 22:36:08 +05:30
862a7d5038
[Single File] Add single file support for Flux Canny, Depth and Fill ( #10288 )
...
update
2024-12-18 19:19:47 +05:30
8304adce2a
Make zeroing prompt embeds for Mochi Pipeline configurable ( #10284 )
...
update
2024-12-18 18:32:53 +05:30
b389f339ec
Fix Doc links in GGUF and Quantization overview docs ( #10279 )
...
* update
* Update docs/source/en/quantization/gguf.md
Co-authored-by: Aryan <aryan@huggingface.co >
---------
Co-authored-by: Aryan <aryan@huggingface.co >
2024-12-18 18:32:36 +05:30
e222246b4e
Fix sigma_last with use_flow_sigmas ( #10267 )
2024-12-18 12:22:10 +00:00
83709d5a06
Flux Control(Depth/Canny) + Inpaint ( #10192 )
...
* flux_control_inpaint - failing test_flux_different_prompts
* removing test_flux_different_prompts?
* fix style
* fix from PR comments
* fix style
* reducing guidance_scale in demo
* Update src/diffusers/pipelines/flux/pipeline_flux_control_inpaint.py
Co-authored-by: hlky <hlky@hlky.ac >
* make
* prepare_latents is not copied from
* update docs
* typos
---------
Co-authored-by: affromero <ubuntu@ip-172-31-17-146.ec2.internal >
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
Co-authored-by: hlky <hlky@hlky.ac >
2024-12-18 09:14:16 +00:00
8eb73c872a
Support pass kwargs to sd3 custom attention processor ( #9818 )
...
* Support pass kwargs to sd3 custom attention processor
---------
Co-authored-by: hlky <hlky@hlky.ac >
Co-authored-by: YiYi Xu <yixu310@gmail.com >
2024-12-17 21:58:33 -10:00
88b015dc9f
Make time_embed_dim of UNet2DModel changeable ( #10262 )
2024-12-17 21:55:18 -10:00
63cdf9c0ba
[chore] fix: reamde -> readme ( #10276 )
...
fix: reamde -> readme
2024-12-18 10:56:08 +05:30
0ac52d6f09
Use torch in get_2d_rotary_pos_embed ( #10155 )
...
* Use `torch` in `get_2d_rotary_pos_embed`
* Add deprecation
2024-12-17 18:26:52 -10:00
ba6fd6eb30
[chore] fix: licensing headers in mochi and ltx ( #10275 )
...
fix: licensing header.
2024-12-18 08:43:57 +05:30
9408aa2dfc
[LoRA] feat: lora support for SANA. ( #10234 )
...
* feat: lora support for SANA.
* make fix-copies
* rename test class.
* attention_kwargs -> cross_attention_kwargs.
* Revert "attention_kwargs -> cross_attention_kwargs."
This reverts commit 23433bf9bcaryan@huggingface.co >
* style
* docs for attention_kwargs.
* remove lora_scale from pag pipeline.
* copy fix
---------
Co-authored-by: Aryan <aryan@huggingface.co >
2024-12-18 08:22:31 +05:30
ec1c7a793f
Add set_shift to FlowMatchEulerDiscreteScheduler ( #10269 )
2024-12-17 21:40:09 +00:00
9c68c945e9
[Community Pipeline] Fix typo that cause error on regional prompting pipeline ( #10251 )
...
fix: fix typo that cause error
2024-12-17 21:09:50 +00:00
2739241ad1
[docs] delete_adapters() ( #10245 )
...
delete_adapters
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2024-12-17 09:26:45 -08:00
1524781b88
[tests] Remove/rename unsupported quantization torchao type ( #10263 )
...
update
2024-12-17 21:43:15 +05:30
128b96f369
Fix Mochi Quality Issues ( #10033 )
...
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* Update src/diffusers/models/transformers/transformer_mochi.py
Co-authored-by: Aryan <aryan@huggingface.co >
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
Co-authored-by: Aryan <aryan@huggingface.co >
2024-12-17 19:40:00 +05:30
e24941b2a7
[Single File] Add GGUF support ( #9964 )
...
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* Update src/diffusers/quantizers/gguf/utils.py
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* Update docs/source/en/quantization/gguf.md
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
* update
* update
* update
* update
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
2024-12-17 16:09:37 +05:30
f9d5a9324d
[docs] Clarify dtypes for Sana ( #10248 )
...
update
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2024-12-17 13:43:24 +05:30
ac86393487
[LoRA] Support LTX Video ( #10228 )
...
* add lora support for ltx
* add tests
* fix copied from comments
* update
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
2024-12-17 12:05:05 +05:30
0d96a894a7
Fix copied from comment in Mochi lora loader ( #10255 )
...
update
2024-12-17 11:09:57 +05:30
6fb94d51cb
[chore] add contribution note for lawrence. ( #10253 )
...
add contribution note for lawrence.
2024-12-17 09:17:40 +05:30
7667cfcb41
[docs] Add missing AttnProcessors ( #10246 )
...
* attnprocessors
* lora
* make style
* fix
* fix
* sana
* typo
2024-12-16 15:36:26 -08:00
9f00c617a0
[core] TorchAO Quantizer ( #10009 )
...
* torchao quantizer
---------
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com >
Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com >
2024-12-16 13:35:40 -10:00
aafed3f8dd
fix downsample bug in MidResTemporalBlock1D ( #10250 )
2024-12-17 04:55:16 +05:30
5ed761a6f2
Add ControlNetUnion to AutoPipeline from_pretrained ( #10219 )
2024-12-16 10:25:08 -10:00
2f023d7b84
Fix RePaint Scheduler ( #10185 )
...
Fix repaint scheduler
2024-12-16 09:38:13 -10:00
e9a3911b67
Fix checkpoint in CogView3PlusPipeline example ( #10211 )
2024-12-16 09:31:22 -10:00
7186bb45f0
Add enable_vae_tiling to AllegroPipeline, fix example ( #10212 )
2024-12-16 09:31:02 -10:00
438bd60549
Use non-human subject in StableDiffusion3ControlNetPipeline example ( #10214 )
...
* Use non-human subject in StableDiffusion3ControlNetPipeline example
* make style
2024-12-16 09:30:26 -10:00
87e8157437
Fix ControlNetUnion _callback_tensor_inputs ( #10218 )
2024-12-16 09:29:12 -10:00
3f421fe09f
Fix use_flow_sigmas ( #10242 )
...
use_flow_sigmas copy
2024-12-16 09:27:22 -10:00
a7d50524dd
Add dynamic_shifting to SD3 ( #10236 )
...
* Add `dynamic_shifting` to SD3
* calculate_shift
* FlowMatchHeunDiscreteScheduler doesn't support mu
* Inpaint/img2img
2024-12-16 09:25:21 -10:00
672bd49573
Use t instead of timestep in _apply_perturbed_attention_guidance ( #10243 )
2024-12-16 09:24:16 -10:00
ea893a9ae7
[Docs] add rest of the lora loader mixins to the docs. ( #10230 )
...
add rest of the lora loader mixins to the docs.
2024-12-16 08:50:27 -08:00
5fb3a98517
Update pipeline_controlnet.py add support for pytorch_xla ( #10222 )
...
* Update pipeline_controlnet.py
* make style
---------
Co-authored-by: hlky <hlky@hlky.ac >
2024-12-16 09:05:50 +00:00
aace1f412b
[core] Hunyuan Video ( #10136 )
...
* copy transformer
* copy vae
* copy pipeline
* make fix-copies
* refactor; make original code work with diffusers; test latents for comparison generated with this commit
* move rope into pipeline; remove flash attention; refactor
* begin conversion script
* make style
* refactor attention
* refactor
* refactor final layer
* their mlp -> our feedforward
* make style
* add docs
* refactor layer names
* refactor modulation
* cleanup
* refactor norms
* refactor activations
* refactor single blocks attention
* refactor attention processor
* make style
* cleanup a bit
* refactor double transformer block attention
* update mochi attn proc
* use diffusers attention implementation in all modules; checkpoint for all values matching original
* remove helper functions in vae
* refactor upsample
* refactor causal conv
* refactor resnet
* refactor
* refactor
* refactor
* grad checkpointing
* autoencoder test
* fix scaling factor
* refactor clip
* refactor llama text encoding
* add coauthor
Co-Authored-By: "Gregory D. Hunkins" <greg@ollano.com >
* refactor rope; diff: 0.14990234375; reason and fix: create rope grid on cpu and move to device
Note: The following line diverges from original behaviour. We create the grid on the device, whereas
original implementation creates it on CPU and then moves it to device. This results in numerical
differences in layerwise debugging outputs, but visually it is the same.
* use diffusers timesteps embedding; diff: 0.10205078125
* rename
* convert
* update
* add tests for transformer
* add pipeline tests; text encoder 2 is not optional
* fix attention implementation for torch
* add example
* update docs
* update docs
* apply suggestions from review
* refactor vae
* update
* Apply suggestions from code review
Co-authored-by: hlky <hlky@hlky.ac >
* Update src/diffusers/pipelines/hunyuan_video/pipeline_hunyuan_video.py
Co-authored-by: hlky <hlky@hlky.ac >
* Update src/diffusers/pipelines/hunyuan_video/pipeline_hunyuan_video.py
Co-authored-by: hlky <hlky@hlky.ac >
* make fix-copies
* update
---------
Co-authored-by: "Gregory D. Hunkins" <greg@ollano.com >
Co-authored-by: hlky <hlky@hlky.ac >
2024-12-16 13:56:18 +05:30
djm